{"total":129,"rows":[{"id":"2504.13837","title":"Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?","created":"2025-04-18","cited_by_count":982,"area":"lr"},{"id":"2504.14945","title":"Learning to Reason under Off-Policy Guidance","created":"2025-04-21","cited_by_count":281,"area":"lr"},{"id":"2506.10947","title":"Spurious Rewards: Rethinking Training Signals in RLVR","created":"2025-06-12","cited_by_count":209,"area":"lr"},{"id":"2505.24864","title":"ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models","created":"2025-05-30","cited_by_count":194,"area":"lr"},{"id":"2506.07527","title":"Learning What Reinforcement Learning Can't: Interleaved Online Fine-Tuning for Hardest Questions","created":"2025-06-09","cited_by_count":97,"area":"lr"},{"id":"2507.14843","title":"The Invisible Leash: Why RLVR May or May Not Escape Its Origin","created":"2025-07-20","cited_by_count":97,"area":null},{"id":"2509.06941","title":"Outcome-based Exploration for LLM Reasoning","created":"2025-09-08","cited_by_count":83,"area":"lr"},{"id":"2512.07783","title":"On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models","created":"2025-12-08","cited_by_count":69,"area":"lr"},{"id":"2508.16949","title":"Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning","created":"2025-08-23","cited_by_count":63,"area":"lr"},{"id":"2507.01679","title":"Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling","created":"2025-07-02","cited_by_count":60,"area":"lr"},{"id":"2506.08446","title":"A Survey on Large Language Models for Mathematical Reasoning","created":"2025-06-10","cited_by_count":52,"area":"lr"},{"id":"2507.13266","title":"QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation","created":"2025-07-17","cited_by_count":44,"area":"lr"},{"id":"2508.13755","title":"Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration","created":"2025-08-19","cited_by_count":43,"area":"lr"},{"id":"2509.25123","title":"From $f(x)$ and $g(x)$ to $f(g(x))$: LLMs Learn New Skills in RL by Composing Old Ones","created":"2025-09-29","cited_by_count":42,"area":null},{"id":"2601.18779","title":"POPE: Learning to Reason on Hard Problems via Privileged On-Policy Exploration","created":"2026-01-26","cited_by_count":42,"area":"lr"},{"id":"2505.18116","title":"NFT: Bridging Supervised Learning and Reinforcement Learning in Math Reasoning","created":"2025-05-23","cited_by_count":38,"area":"lr"},{"id":"2602.02710","title":"Maximum Likelihood Reinforcement Learning","created":"2026-02-02","cited_by_count":36,"area":"deeprl"},{"id":"2509.16679","title":"Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle","created":"2025-09-20","cited_by_count":35,"area":null},{"id":"2509.23024","title":"Tracing the Representation Geometry of Language Models from Pretraining to Post-training","created":"2025-09-27","cited_by_count":35,"area":null},{"id":"2507.05255","title":"Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning","created":"2025-07-07","cited_by_count":34,"area":"lr"},{"id":"2509.21128","title":"RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs","created":"2025-09-25","cited_by_count":34,"area":"lr"},{"id":"2510.20817","title":"KL-Regularized Reinforcement Learning is Designed to Mode Collapse","created":"2025-10-23","cited_by_count":31,"area":"deeprl"},{"id":"2510.07364","title":"Base Models Know How to Reason, Thinking Models Learn When","created":"2025-10-08","cited_by_count":27,"area":"lr"},{"id":"2509.25666","title":"Nudging the Boundaries of LLM Reasoning","created":"2025-09-30","cited_by_count":26,"area":"lr"},{"id":"2505.20686","title":"Accelerating RL for LLM Reasoning with Optimal Advantage Regression","created":"2025-05-27","cited_by_count":24,"area":"lr"},{"id":"2508.21048","title":"Veritas: Generalizable Deepfake Detection via Pattern-Aware Reasoning","created":"2025-08-28","cited_by_count":23,"area":"lr"},{"id":"2511.19942","title":"Differential Smoothing Mitigates Sharpening and Improves LLM Reasoning","created":"2025-11-25","cited_by_count":22,"area":"lr"},{"id":"2511.12344","title":"Reward and Guidance through Rubrics: Promoting Exploration to Improve Multi-Domain Reasoning","created":"2025-11-15","cited_by_count":21,"area":"lr"},{"id":"2505.16826","title":"KTAE: A Model-Free Algorithm to Key-Tokens Advantage Estimation in Mathematical Reasoning","created":"2025-05-22","cited_by_count":19,"area":"lr"},{"id":"2512.23333","title":"CME-CAD: Heterogeneous Collaborative Multi-Expert Reinforcement Learning for CAD Code Generation","created":"2025-12-29","cited_by_count":19,"area":null},{"id":"2506.13923","title":"Adaptive Guidance Accelerates Reinforcement Learning of Reasoning Models","created":"2025-06-16","cited_by_count":18,"area":"lr"},{"id":"2509.14234","title":"Compute as Teacher: Turning Inference Compute Into Reference-Free Supervision","created":"2025-09-17","cited_by_count":18,"area":null},{"id":"2510.02230","title":"The Reasoning Boundary Paradox: How Reinforcement Learning Constrains Language Models","created":"2025-10-02","cited_by_count":18,"area":"lr"},{"id":"2601.18795","title":"Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes","created":"2026-01-26","cited_by_count":16,"area":"lr"},{"id":"2507.10616","title":"Scalpel vs. Hammer: GRPO Amplifies Existing Capabilities, SFT Replaces Them","created":"2025-07-13","cited_by_count":15,"area":"lr"},{"id":"2605.10781","title":"Rebellious Student: Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVR","created":"2026-05-11","cited_by_count":15,"area":"lr"},{"id":"2505.14216","title":"Reinforcement Learning vs. Distillation: Understanding Accuracy and Capability in LLM Reasoning","created":"2025-05-20","cited_by_count":14,"area":"lr"},{"id":"2505.19406","title":"Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model","created":"2025-05-26","cited_by_count":14,"area":"lr"},{"id":"2508.09670","title":"MEML-GRPO: Heterogeneous Multi-Expert Mutual Learning for RLVR Advancement","created":"2025-08-13","cited_by_count":14,"area":"lr"},{"id":"2510.09388","title":"Don't Tell the Answer, Truly Guide the Reasoning During RL Rollouts","created":"2025-10-10","cited_by_count":14,"area":"lr"},{"id":"2505.24273","title":"How Much Backtracking is Enough? Exploring the Interplay of SFT and RL in Enhancing LLM Reasoning","created":"2025-05-30","cited_by_count":13,"area":"lr"},{"id":"2507.02834","title":"ExPO: Unlocking Hard Reasoning with Self-Explanation-Guided Reinforcement Learning","created":"2025-07-03","cited_by_count":13,"area":"lr"},{"id":"2510.04028","title":"The Debate on RLVR Reasoning Capability Boundary: Shrinkage, Expansion, or Both? A Two-Stage Dynamic View","created":"2025-10-05","cited_by_count":13,"area":"lr"},{"id":"2601.18778","title":"Teaching Models to Teach Themselves: Reasoning at the Edge of Learnability","created":"2026-01-26","cited_by_count":13,"area":"lr"},{"id":"2506.04695","title":"Reshaping Reasoning in LLMs: A Theoretical Analysis of RL Training Dynamics through Pattern Selection","created":"2025-06-05","cited_by_count":12,"area":"lr"},{"id":"2509.21882","title":"Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards","created":"2025-09-26","cited_by_count":12,"area":null},{"id":"2602.01058","title":"Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning","created":"2026-02-01","cited_by_count":11,"area":"lr"},{"id":"2602.04705","title":"ERNIE 5.0 Technical Report","created":"2026-02-04","cited_by_count":11,"area":"moe"},{"id":"2603.11682","title":"Entropy-Preserving Reinforcement Learning","created":"2026-03-12","cited_by_count":11,"area":"lr"},{"id":"2510.05251","title":"Let it Calm: Exploratory Annealed Decoding for Verifiable Reinforcement Learning","created":"2025-10-06","cited_by_count":10,"area":"lr"},{"id":"2510.26707","title":"Value Drifts: Tracing Value Alignment During LLM Post-Training","created":"2025-10-30","cited_by_count":10,"area":"alignment"},{"id":"2603.10263","title":"From Prior to Pro: Efficient Skill Mastery via Distribution Contractive RL Finetuning","created":"2026-03-10","cited_by_count":10,"area":"deeprl"},{"id":"2507.00726","title":"Can Large Language Models Develop Strategic Reasoning? Post-training Insights from Learning Chess","created":"2025-07-01","cited_by_count":9,"area":"lr"},{"id":"2507.20187","title":"Diversity-Enhanced Reasoning for Subjective Questions","created":"2025-07-27","cited_by_count":9,"area":"lr"},{"id":"2604.23747","title":"SFT-then-RL Outperforms Mixed-Policy Methods for LLM Reasoning","created":"2026-04-26","cited_by_count":9,"area":"lr"},{"id":"2505.18917","title":"Behavior Injection: Preparing Language Models for Reinforcement Learning","created":"2025-05-25","cited_by_count":8,"area":"lr"},{"id":"2508.07809","title":"EvoCoT: Overcoming the Exploration Bottleneck in Reinforcement Learning","created":"2025-08-11","cited_by_count":7,"area":"lr"},{"id":"2508.08641","title":"MiGrATe: Mixed-Policy GRPO for Adaptation at Test-Time","created":"2025-08-12","cited_by_count":7,"area":"lr"},{"id":"2509.25424","title":"Polychromic Objectives for Reinforcement Learning","created":"2025-09-29","cited_by_count":7,"area":"deeprl"},{"id":"2602.01705","title":"LaDi-RL: Latent Diffusion Reasoning Prevents Entropy Collapse in Reinforcement Learning","created":"2026-02-02","cited_by_count":7,"area":"lr"},{"id":"2602.04755","title":"When Silence Is Golden: Can LLMs Learn to Abstain in Temporal QA and Beyond?","created":"2026-02-04","cited_by_count":7,"area":null},{"id":"2506.09967","title":"Resa: Transparent Reasoning Models via SAEs","created":"2025-06-11","cited_by_count":6,"area":"lr"},{"id":"2602.03249","title":"Accordion-Thinking: Self-Regulated Step Summaries for Efficient and Readable LLM Reasoning","created":"2026-02-03","cited_by_count":6,"area":"lr"},{"id":"2603.03078","title":"RAPO: Expanding Exploration for LLM Agents via Retrieval-Augmented Policy Optimization","created":"2026-03-03","cited_by_count":6,"area":"rag"},{"id":"2606.18967","title":"EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts","created":"2026-06-17","cited_by_count":6,"area":"lr"},{"id":"2506.15710","title":"RAST: Reasoning Activation in LLMs via Small-model Transfer","created":"2025-05-30","cited_by_count":5,"area":"lr"},{"id":"2510.15990","title":"Can GRPO Help LLMs Transcend Their Pretraining Origin?","created":"2025-10-14","cited_by_count":5,"area":"lr"},{"id":"2604.17654","title":"Poly-EPO: Training Exploratory Reasoning Models","created":"2026-04-19","cited_by_count":5,"area":"lr"},{"id":"2505.13718","title":"Warm Up Before You Train: Unlocking General Reasoning in Resource-Constrained Settings","created":"2025-05-19","cited_by_count":4,"area":"lr"},{"id":"2506.10378","title":"Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning","created":"2025-06-12","cited_by_count":4,"area":null},{"id":"2509.04027","title":"Why Does Reasoning Length Converge? Unveiling the Underfitting-Overfitting Trade-off in Chain-of-Thought","created":"2025-09-04","cited_by_count":4,"area":"lr"},{"id":"2510.20909","title":"Code-enabled language models can outperform reasoning models on diverse tasks","created":"2025-10-23","cited_by_count":4,"area":"lr"},{"id":"2511.05933","title":"Reinforcement Learning Improves Traversal of Parametric Knowledge in LLMs","created":"2025-11-08","cited_by_count":4,"area":null},{"id":"2511.12429","title":"Tailored Primitive Initialization is the Secret Key to Reinforcement Learning","created":"2025-11-16","cited_by_count":4,"area":"lr"},{"id":"2601.09361","title":"GeoRA: Geometry-Aware Low-Rank Adaptation for RLVR","created":"2026-01-14","cited_by_count":4,"area":"lr"},{"id":"2602.03978","title":"Monitorability as a Free Gift: How RLVR Spontaneously Aligns Reasoning","created":"2026-02-03","cited_by_count":4,"area":"lr"},{"id":"2604.04767","title":"Cog-DRIFT: Exploration on Adaptively Reformulated Instances Enables Learning from Hard Reasoning Problems","created":"2026-04-06","cited_by_count":4,"area":"lr"},{"id":"2605.17026","title":"Why Do Reasoning Models Lose Coverage? The Role of Data and Forks in the Road","created":"2026-05-16","cited_by_count":4,"area":"lr"},{"id":"2505.17988","title":"Towards Revealing the Effectiveness of Small-Scale Fine-tuning in R1-style Reinforcement Learning","created":"2025-05-23","cited_by_count":3,"area":"lr"},{"id":"2506.20666","title":"Cognitive models can reveal interpretable value trade-offs in language models","created":"2025-06-25","cited_by_count":3,"area":null},{"id":"2510.15979","title":"Cog-Rethinker: Hierarchical Metacognitive Reinforcement Learning for LLM Reasoning","created":"2025-10-13","cited_by_count":3,"area":"lr"},{"id":"2603.12248","title":"Matching Features, Not Tokens: Energy-Based Fine-Tuning of Language Models","created":"2026-03-12","cited_by_count":3,"area":null},{"id":"2604.16243","title":"Find, Fix, Reason: Context Repair for Video Reasoning","created":"2026-04-17","cited_by_count":3,"area":"mllm"},{"id":"2607.20543","title":"When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion","created":"2026-07-12","cited_by_count":3,"area":null},{"id":"2509.21124","title":"Expanding Reasoning Potential in Foundation Model by Learning Diverse Chains of Thought Patterns","created":"2025-09-25","cited_by_count":2,"area":"lr"},{"id":"2601.04670","title":"Learning Dynamics in RL Post-Training for Language Models","created":"2026-01-08","cited_by_count":2,"area":"lr"},{"id":"2601.18129","title":"Typhoon-S: Minimal Open Post-Training for Sovereign Large Language Models","created":"2026-01-26","cited_by_count":2,"area":null},{"id":"2602.00533","title":"Convergent World Representations and Divergent Tasks","created":"2026-01-31","cited_by_count":2,"area":null},{"id":"2602.08281","title":"New Skills or Sharper Primitives? A Probabilistic Perspective on the Emergence of Reasoning in RLVR","created":"2026-02-09","cited_by_count":2,"area":"lr"},{"id":"2605.16874","title":"Reasoning Can Be Restored by Correcting a Few Decision Tokens","created":"2026-05-16","cited_by_count":2,"area":"lr"},{"id":"2606.03962","title":"Using Reward Uncertainty to Induce Diverse Behaviour in Reinforcement Learning","created":"2026-06-02","cited_by_count":2,"area":"alignment"},{"id":"2606.06080","title":"On Advantage Estimates for Max@K Policy Gradients","created":"2026-06-04","cited_by_count":2,"area":"lr"},{"id":"2606.06096","title":"OrderGrad: Optimizing Beyond the Mean with Order-Statistic Policy Gradient Estimation","created":"2026-06-04","cited_by_count":2,"area":"deeprl"},{"id":"2606.13125","title":"Select and Improve: Understanding the Mechanics of Post-Training for Reasoning","created":"2026-06-11","cited_by_count":2,"area":null},{"id":"2608.24949","title":"Demystifying Reinforcement Learning Post-Training of Language Models","created":"2026-08-24","cited_by_count":2,"area":"lr"},{"id":"2608.25756","title":"TailSFT: Filtered Fine-Tuning Improves Post-Training Performance","created":"2026-08-26","cited_by_count":2,"area":"agents"},{"id":"2508.18672","title":"Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks","created":"2025-08-26","cited_by_count":1,"area":"lr"},{"id":"2511.00710","title":"Does RLVR Extend Reasoning Boundaries? Investigating Capability Expansion in Vision-Language Models","created":"2025-11-01","cited_by_count":1,"area":"lr"},{"id":"2601.21476","title":"Thinking Seeds: Leveraging Historical Diversity for Position-Aware RL in LLMs","created":"2026-01-29","cited_by_count":1,"area":"lr"},{"id":"2602.20197","title":"Controllable Exploration in Hybrid-Policy RLVR for Multi-Modal Reasoning","created":"2026-02-22","cited_by_count":1,"area":"lr"}],"next_cursor":"100"}